Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
What's new
10
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Open sidebar
grp-bio-it
image-analysis-training-resources
Commits
b4009968
Commit
b4009968
authored
Jul 18, 2019
by
Christian Tischer
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'pixel_neighbourhood_conversion' into 'master'
Pixel neighbourhood conversion See merge request
!40
parents
45f75824
0dc926ca
Pipeline
#10611
passed with stage
in 1 minute and 12 seconds
Changes
2
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
44 additions
and
33 deletions
+44
-33
_includes/filter_neighbourhood/activities/mean_filter_imagejgui.md
.../filter_neighbourhood/activities/mean_filter_imagejgui.md
+6
-0
_modules/filter_neighbourhood.md
_modules/filter_neighbourhood.md
+38
-33
No files found.
_includes/filter_neighbourhood/activities/mean_filter_imagejgui.md
0 → 100644
View file @
b4009968
-
**[ Open... ]**
"/image-analysis-training-resources/image_data/xy_8bit__nuclei_noisy_different_intensity.tif"
-
Appreciate that you cannot readily apply a threshold to binarize the image into two nuclei and background
-
Apply a mean filter
**[ Mean]**
-
Try different neighbourhood sizes for mean filter
-
Appreciate that the filtered pixel values are slightly wrong due to integer data type
-
Binarize the filtered image by applying a threshold ()
_modules/filter_neighbourhood.md
View file @
b4009968
---
title
:
Neighbourhood image filters
layout
:
page
permalink
:
/filtersneighbourhood
---
# Neighborhood filters
## Requirements
-
Pixel properties
## Motivation
This module explains how image features (objects) can be enhanced using filters
layout
:
module
prerequisites
:
-
"
[Image
pixels](image_pixels)"
objectives
:
-
Understand the basic principle of a neighbourhood filter
motivation
:
>
This module explains how image features (objects) can be enhanced using filters
## Learning objectives
-
Understand the basic principle of a neighbourhood filter.
## Concept map
```
mermaid
graph TB
P(pixel) --> |has| NBH(neighbourhood pixels)
NBH --> |are used in| A(mathematical formula)
A --> |compute new| NP(pixel value)
```
|
|
|
|
|
|
|
|
|
|
---|---|---|---|---|---|---|---|
...
...
@@ -37,15 +19,38 @@ graph TB
|
| | | | NB | NB | NB | |
|
| | | | | | | |
## Example
c
oncept_map: >
graph TB
P(pixel) --> |has| NBH(neighbourhood pixels)
NBH --> |are used in| A(mathematical formula)
A --> |compute new| NP(pixel value)
#
figure: /figures/binarization.png
#
figure_legend: Image before and after binarization by applying a threshold.
a
ctivity_preface: >
Use mean filter to facilitate image binarization
a
ctivities:
"ImageJ GUI": "filter_nighbourhood/activities/mean_filter_imagejgui.md"
#
"ImageJ Macro":
#
"Jython":
#
"MATLAB":
e
xercises_preface: >
TODO: Mean filter image
e
xercises:
#
"ImageJ GUI":
#
"ImageJ Macro":
#
"Jython":
#
"MATLAB":
## Activity: Use mean filter to facilitate image binarization
l
earn_next:
-
"[Convolution filters](filter_convolution)"
-
"[Rank filters](filter_rank)"
*
Open image: xy_8bit__nuclei_noisy_different_intensity.tif
*
Appreciate that you cannot readily apply a threshold to binarize the image into two nuclei and background
*
Apply a mean filter, exploring different neighbourhood sizes
*
Appreciate that the filtered pixel values are slightly wrong due to integer data type
*
Binarize the filtered image by applying a threshold
e
xternal_links:
-
--
\ No newline at end of file
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment